Maximum Entropy-based (MaxEnt) Classifier

A Maximum Entropy-based (MaxEnt) Classifier is a discriminative classifier that is based on Maximum Entropy optimization.

• Context:
  • It can be produces by a Maximum Entropy-based Learning Algorithm.
  • It is based on the Maximum Entropy Principle.
• Example(s):
  • a Regressed Logistic Model.
  • a Maximum Entropy Markov_Model.
• See: Conditional Random Fields, MEMM/Maximum Entropy Markov Models, Maximum Entropy-based Learning Algorithm.

---

---

References

1996

• (Berger et al., 1996) ⇒ Adam L. Berger, Vincent J. Della Pietra, and Stephen A. Della Pietra. (1996). “A Maximum Entropy Approach to Natural Language Processing.” In: Computational Linguistics, 22(1).

---